[repost ]Deep Learning and Shallow Learning
original:http://freemind.pluskid.org/machine-learning/deep-learning-and-shallow-learning/ 由于 Deep Learning 现在如火如荼的势头,在各种领域逐渐占据 state-of-the-art 的地位,上个学期在一门课的 project 中见识过了 deep learning 的效果,最近在做一个东西的时候模型上遇到一点瓶颈于是终于决定也来了解一下这个魔幻的领域。 据说 Deep Learning 的 break through 大概可以从 Hinton 在 2006 年提出的用于训练 Deep Belief Network (DBN) 的算法开始,打破了持续了数十年的多层神经网络效果很差的尴尬局面,其之后各种其他的算法和模型也相继被提出来并在各个应用领域中大展神威。而近来 Google 聘请 Hinton、纽约时报的封面报道等公众媒体的宣传,更是使得 deep learning 变得大红大紫。记得之前在老板的某个 draft 中看到过这样一段话: I do not expect that this paper will ever be published in the usual journals. “Success” for a paper [...]
via WordPress http://blog.newitfarmer.com/ai/deep-learning/13035/repost-deep-learning-and-shallow-learning-2#utm_source=rss&utm_medium=rss&utm_campaign=repost-deep-learning-and-shallow-learning-2
via WordPress http://blog.newitfarmer.com/ai/deep-learning/13035/repost-deep-learning-and-shallow-learning-2#utm_source=rss&utm_medium=rss&utm_campaign=repost-deep-learning-and-shallow-learning-2
Labels: hanhuiwen
0 Comments:
Post a Comment
<< Home